Kimi sentiment tracking
Long answers give the classifier real material to work with, so Kimi produces the highest-confidence sentiment labels of any engine we track.
How it renders
Derived from the source-language answer text with the evidence passage retained.
Sampling
Classifications are reported as distributions across n, because the same engine will frame the same brand differently between samples.
Gotcha
What the API returns
A single collection call against Kimi for the sentiment field, sampled n times and returned as one object per prompt.
{
"engine": "kimi",
"field": "sentiment",
"prompt": "best ai visibility tracking tool",
"country": "GB",
"language": "en",
"n": 30,
"sentiment": [
{
"brand": "Nostimates",
"label": "recommended",
"confidence": 0.86,
"distribution": {
"recommended": 0.6,
"neutral": 0.33,
"hedged": 0.07
}
}
]
}Response fields
| Key | Type | Notes |
|---|---|---|
| brand | string | Brand the classification applies to. |
| label | string | recommended | neutral | hedged | negative. |
| confidence | float | Classifier confidence for this sample. |
| evidence | string | The sentence the label was drawn from. |
| distribution | object | Label shares across the n samples. |
What it costs
Add-on field. Priced per collection at a small multiple of the base credit.
See credit pricing →Kimi sentiment FAQ
- Can one answer be both positive and negative?
- On Kimi, frequently. We label per passage instead of forcing a single verdict.
- Is confidence higher here?
- Yes, materially, because there is more text per judgement.
Get passage-level sentiment from long answers
Send a technical prompt set and we will return per-passage labels with evidence.
Other Kimi data
Across every engine
Compare how sentiment behaves on every engine we track.
Sentiment across all engines →